Discovering Adaptable Symbolic Algorithms from Scratch

by   Stephen Kelly, et al.

Autonomous robots deployed in the real world will need control policies that rapidly adapt to environmental changes. To this end, we propose AutoRobotics-Zero (ARZ), a method based on AutoML-Zero that discovers zero-shot adaptable policies from scratch. In contrast to neural network adaption policies, where only model parameters are optimized, ARZ can build control algorithms with the full expressive power of a linear register machine. We evolve modular policies that tune their model parameters and alter their inference algorithm on-the-fly to adapt to sudden environmental changes. We demonstrate our method on a realistic simulated quadruped robot, for which we evolve safe control policies that avoid falling when individual limbs suddenly break. This is a challenging task in which two popular neural network baselines fail. Finally, we conduct a detailed analysis of our method on a novel and challenging non-stationary control task dubbed Cataclysmic Cartpole. Results confirm our findings that ARZ is significantly more robust to sudden environmental changes and can build simple, interpretable control policies.


Using Simulation Optimization to Improve Zero-shot Policy Transfer of Quadrotors

In this work, we show that it is possible to train low-level control pol...

Hardware Conditioned Policies for Multi-Robot Transfer Learning

Deep reinforcement learning could be used to learn dexterous robotic pol...

Simultaneously Learning Vision and Feature-based Control Policies for Real-world Ball-in-a-Cup

We present a method for fast training of vision based control policies o...

Domain Randomization for Robust, Affordable and Effective Closed-loop Control of Soft Robots

Soft robots are becoming extremely popular thanks to their intrinsic saf...

Re-purposing Compact Neuronal Circuit Policies to Govern Reinforcement Learning Tasks

We propose an effective method for creating interpretable control agents...

Graph Policy Gradients for Large Scale Robot Control

In this paper, we consider the problem of learning policies to control a...

Zero-Shot Policy Transferability for the Control of a Scale Autonomous Vehicle

We report on a study that employs an in-house developed simulation infra...

Please sign up or login with your details

Forgot password? Click here to reset